aboutsummaryrefslogtreecommitdiff
path: root/src/urlglob.c
blob: 48974d1fa1b24fef3bdab4f0a0a48fd403ac7e61 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
/*****************************************************************************
 *                                  _   _ ____  _     
 *  Project                     ___| | | |  _ \| |    
 *                             / __| | | | |_) | |    
 *                            | (__| |_| |  _ <| |___ 
 *                             \___|\___/|_| \_\_____|
 *
 *  The contents of this file are subject to the Mozilla Public License
 *  Version 1.0 (the "License"); you may not use this file except in
 *  compliance with the License. You may obtain a copy of the License at
 *  http://www.mozilla.org/MPL/
 *
 *  Software distributed under the License is distributed on an "AS IS"
 *  basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
 *  License for the specific language governing rights and limitations
 *  under the License.
 *
 *  The Original Code is Curl.
 *
 *  The Initial Developer of the Original Code is Daniel Stenberg.
 *
 *  Portions created by the Initial Developer are Copyright (C) 1998.
 *  All Rights Reserved.
 *
 * ------------------------------------------------------------
 * Main author:
 * - Daniel Stenberg <Daniel.Stenberg@haxx.nu>
 *
 * 	http://curl.haxx.nu
 *
 * $Source$
 * $Revision$
 * $Date$
 * $Author$
 * $State$
 * $Locker$
 *
 * ------------------------------------------------------------
 ****************************************************************************/

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <curl/curl.h>
#include "urlglob.h"

char glob_buffer[URL_MAX_LENGTH];
URLGlob *glob_expand;

int glob_word(char*, int);

int glob_set(char *pattern, int pos) {
  /* processes a set expression with the point behind the opening '{'
     ','-separated elements are collected until the next closing '}'
  */
  char* buf = glob_buffer;
  URLPattern *pat;

  pat = (URLPattern*)&glob_expand->pattern[glob_expand->size / 2];
  /* patterns 0,1,2,... correspond to size=1,3,5,... */
  pat->type = UPTSet;
  pat->content.Set.size = 0;
  pat->content.Set.ptr_s = 0;
  pat->content.Set.elements = (char**)malloc(0);
  ++glob_expand->size;

  while (1) {
    switch (*pattern) {
    case '\0':				/* URL ended while set was still open */
      printf("error: unmatched brace at pos %d\n", pos);
      exit (URG_URL_MALFORMAT);
    case '{':
    case '[':				/* no nested expressions at this time */
      printf("error: nested braces not supported %d\n", pos);
      exit (URG_URL_MALFORMAT);
    case ',':
    case '}':				/* set element completed */
      *buf = '\0';
      pat->content.Set.elements = realloc(pat->content.Set.elements, (pat->content.Set.size + 1) * sizeof(char*));
      if (!pat->content.Set.elements) {
	printf("out of memory in set pattern\n");
	exit(URG_OUT_OF_MEMORY);
      }
      pat->content.Set.elements[pat->content.Set.size] = strdup(glob_buffer);
      ++pat->content.Set.size;

      if (*pattern == '}')		/* entire set pattern completed */
	/* always check for a literal (may be "") between patterns */
	return pat->content.Set.size * glob_word(++pattern, ++pos);

      buf = glob_buffer;
      ++pattern;
      ++pos;
      break;
    case ']':				/* illegal closing bracket */
      printf("error: illegal pattern at pos %d\n", pos);
      exit (URG_URL_MALFORMAT);
    case '\\':				/* escaped character, skip '\' */
      if (*(buf+1) == '\0') {		/* but no escaping of '\0'! */
	printf("error: illegal pattern at pos %d\n", pos);
	exit (URG_URL_MALFORMAT);
      }
      ++pattern;
      ++pos;				/* intentional fallthrough */
    default:
      *buf++ = *pattern++;		/* copy character to set element */
      ++pos;
    }
  }
  exit (URG_FAILED_INIT);
}

int glob_range(char *pattern, int pos) {
  /* processes a range expression with the point behind the opening '['
     - char range: e.g. "a-z]", "B-Q]"
     - num range: e.g. "0-9]", "17-2000]"
     - num range with leading zeros: e.g. "001-999]"
     expression is checked for well-formedness and collected until the next ']'
  */
  URLPattern *pat;
  char *c;
  
  pat = (URLPattern*)&glob_expand->pattern[glob_expand->size / 2];
  /* patterns 0,1,2,... correspond to size=1,3,5,... */
  ++glob_expand->size;

  if (isalpha((int)*pattern)) {		/* character range detected */
    pat->type = UPTCharRange;
    if (sscanf(pattern, "%c-%c]", &pat->content.CharRange.min_c, &pat->content.CharRange.max_c) != 2 ||
	pat->content.CharRange.min_c >= pat->content.CharRange.max_c ||
	pat->content.CharRange.max_c - pat->content.CharRange.min_c > 'z' - 'a') {
      /* the pattern is not well-formed */ 
      printf("error: illegal pattern or range specification after pos %d\n", pos);
      exit (URG_URL_MALFORMAT);
    }
    pat->content.CharRange.ptr_c = pat->content.CharRange.min_c;
    /* always check for a literal (may be "") between patterns */
    return (pat->content.CharRange.max_c - pat->content.CharRange.min_c + 1) *
      glob_word(pattern + 4, pos + 4);
  }
  if (isdigit((int)*pattern)) {		/* numeric range detected */
    pat->type = UPTNumRange;
    pat->content.NumRange.padlength = 0;
    if (sscanf(pattern, "%d-%d]", &pat->content.NumRange.min_n, &pat->content.NumRange.max_n) != 2 ||
	pat->content.NumRange.min_n >= pat->content.NumRange.max_n) {
      /* the pattern is not well-formed */ 
      printf("error: illegal pattern or range specification after pos %d\n", pos);
      exit (URG_URL_MALFORMAT);
    }
    if (*pattern == '0') {		/* leading zero specified */
      c = pattern;  
      while (isdigit((int)*c++))
	++pat->content.NumRange.padlength;	/* padding length is set for all instances
						   of this pattern */
    }
    pat->content.NumRange.ptr_n = pat->content.NumRange.min_n;
    c = (char*)(strchr(pattern, ']') + 1);	/* continue after next ']' */
    /* always check for a literal (may be "") between patterns */
    return (pat->content.NumRange.max_n - pat->content.NumRange.min_n + 1) *
      glob_word(c, pos + (c - pattern));
  }
  printf("error: illegal character in range specification at pos %d\n", pos);
  exit (URG_URL_MALFORMAT);
}

int glob_word(char *pattern, int pos) {
  /* processes a literal string component of a URL
     special characters '{' and '[' branch to set/range processing functions
   */ 
  char* buf = glob_buffer;
  int litindex;

  while (*pattern != '\0' && *pattern != '{' && *pattern != '[') {
    if (*pattern == '}' || *pattern == ']') {
      printf("illegal character at position %d\n", pos);
      exit (URG_URL_MALFORMAT);
    }
    if (*pattern == '\\') {		/* escape character, skip '\' */
      ++pattern;
      ++pos;
      if (*pattern == '\0') {		/* but no escaping of '\0'! */
	printf("illegal character at position %d\n", pos);
	exit (URG_URL_MALFORMAT);
      }
    }
    *buf++ = *pattern++;		/* copy character to literal */
    ++pos;
  }
  *buf = '\0';
  litindex = glob_expand->size / 2;
  /* literals 0,1,2,... correspond to size=0,2,4,... */
  glob_expand->literal[litindex] = strdup(glob_buffer);
  ++glob_expand->size;
  if (*pattern == '\0')
    return 1;				/* singular URL processed  */
  if (*pattern == '{') {
    return glob_set(++pattern, ++pos);	/* process set pattern */
  }
  if (*pattern == '[') {
    return glob_range(++pattern, ++pos);/* process range pattern */
  }
  printf("internal error\n");
  exit (URG_FAILED_INIT);
}

int glob_url(URLGlob** glob, char* url) {
  int urlnum;		/* counts instances of a globbed pattern */

  glob_expand = (URLGlob*)malloc(sizeof(URLGlob));
  glob_expand->size = 0;
  urlnum = glob_word(url, 1);
  *glob = glob_expand;
  return urlnum;
}

char *next_url(URLGlob *glob) {
  static int beenhere = 0;
  char *buf = glob_buffer;
  URLPattern *pat;
  char *lit;
  signed int i;
  int carry;

  if (!beenhere)
    beenhere = 1;
  else {
    carry = 1;

    /* implement a counter over the index ranges of all patterns,
       starting with the rightmost pattern */
    for (i = glob->size / 2 - 1; carry && i >= 0; --i) {
      carry = 0;
      pat = &glob->pattern[i];
      switch (pat->type) {
      case UPTSet:
	if (++pat->content.Set.ptr_s == pat->content.Set.size) {
	  pat->content.Set.ptr_s = 0;
	  carry = 1;
	}
	break;
      case UPTCharRange:
	if (++pat->content.CharRange.ptr_c > pat->content.CharRange.max_c) {
	  pat->content.CharRange.ptr_c = pat->content.CharRange.min_c;
	  carry = 1;
	}
	break;
      case UPTNumRange:
	if (++pat->content.NumRange.ptr_n > pat->content.NumRange.max_n) {
	  pat->content.NumRange.ptr_n = pat->content.NumRange.min_n;
	  carry = 1;
	}
	break;
      default:
	printf("internal error: invalid pattern type (%d)\n", pat->type);
	exit (URG_FAILED_INIT);
      }
    }
    if (carry)		/* first pattern ptr has run into overflow, done! */
      return NULL;
  }

  for (i = 0; i < glob->size; ++i) {
    if (!(i % 2)) {			/* every other term (i even) is a literal */
      lit = glob->literal[i/2];
      strcpy(buf, lit);
      buf += strlen(lit);
    }
    else {				/* the rest (i odd) are patterns */
      pat = &glob->pattern[i/2];
      switch(pat->type) {
      case UPTSet:
	strcpy(buf, pat->content.Set.elements[pat->content.Set.ptr_s]);
	buf += strlen(pat->content.Set.elements[pat->content.Set.ptr_s]);
	break;
      case UPTCharRange:
	*buf++ = pat->content.CharRange.ptr_c;
	break;
      case UPTNumRange:
	sprintf(buf, "%0*d", pat->content.NumRange.padlength, pat->content.NumRange.ptr_n); 
        buf += strlen(buf); /* make no sprint() return code assumptions */
	break;
      default:
	printf("internal error: invalid pattern type (%d)\n", pat->type);
	exit (URG_FAILED_INIT);
      }
    }
  }
  *buf = '\0';
  return strdup(glob_buffer);
}

char *match_url(char *filename, URLGlob glob) {
  char *buf = glob_buffer;
  URLPattern pat;
  int i;

  while (*filename != '\0') {
    if (*filename == '#') {
      if (!isdigit((int)*++filename) ||
	  *filename == '0') {		/* only '#1' ... '#9' allowed */
	printf("illegal matching expression\n");
	exit(URG_URL_MALFORMAT);
      }
      i = *filename - '1';
      if (i + 1 > glob.size / 2) {
	printf("match against nonexisting pattern\n");
	exit(URG_URL_MALFORMAT);
      }
      pat = glob.pattern[i];
      switch (pat.type) {
      case UPTSet:
	strcpy(buf, pat.content.Set.elements[pat.content.Set.ptr_s]);
	buf += strlen(pat.content.Set.elements[pat.content.Set.ptr_s]);
	break;
      case UPTCharRange:
	*buf++ = pat.content.CharRange.ptr_c;
	break;
      case UPTNumRange:
	sprintf(buf, "%0*d", pat.content.NumRange.padlength, pat.content.NumRange.ptr_n);
        buf += strlen(buf);
	break;
      default:
	printf("internal error: invalid pattern type (%d)\n", pat.type);
	exit (URG_FAILED_INIT);
      }
      ++filename;
    }
    else
      *buf++ = *filename++;
  }
  *buf = '\0';
  return strdup(glob_buffer);
}